telephony

Provision Twilio numbers, SMS/MMS, and AI outbound calls.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/productivity/telephony/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill whose verified commands cover all workflows and providers, with strong safety rules and decision-tree guidance. Its main weakness is redundancy: setup commands and the TTS-call workflow are each repeated multiple times, which could be trimmed to roughly half the length without losing clarity.

Suggestions

Cut Workflow A, which duplicates the Provider setup commands verbatim; instead link back to the setup section with a short resume note.

Consolidate Section E, which describes the same Hermes TTS to Twilio Play flow three times (recommended workflow, example agent flow, and hosting options), into one numbered sequence.

Trim the "What this solves" section, which restates the intro bullet list, and remove the meta commentary about keeping telephony out of the core tool list.

Dimension	Reasoning	Score
Conciseness	The body is command-dense with no tutorial-style explanations of known concepts, but contains several redundant sections: "What this solves" restates the intro bullet list, Workflow A repeats the Provider setup commands verbatim, and Section E states the same TTS-to-Play workflow three times. This fits the mostly-efficient-but-could-be-tightened anchor rather than the noticeably-padded anchor 2.	3 / 5
Actionability	Every workflow gives copy-paste-ready, executable commands with concrete flags and example values (e.g. `twilio-buy "+17025551234" --save-env`, `ai-call ... --provider bland --max-duration 3`), and all referenced subcommands exist in scripts/telephony.py. Common cases across all three providers are covered, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Sequences are clear with most checkpoints present: `diagnose` on session resume, mandatory user confirmation before dialing/texting, and a post-setup verification checklist. It falls short of 5 because polling guidance ("Poll for results if needed") is vague and no explicit ai-status retry loop is given.	4 / 5
Progressive Disclosure	Structure is good for a single-script skill: the script path is explicitly located (find command), usage is fully signaled, and sections are clearly organized with no nested references. Minor gap: at ~400 lines, provider setup details and decision-tree rationale could be offloaded to a reference file to keep SKILL.md a leaner overview.	4 / 5
	Total	16 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A terse, distinctive, third-person description that names concrete capabilities but omits any "Use when..." trigger guidance. Adding an explicit trigger clause and natural synonyms like "text/texting" or "voice" would raise completeness and trigger coverage.

Suggestions

Append a trigger clause, e.g. "Use when the user asks to send texts/SMS, make phone calls, buy or manage Twilio numbers, or place AI voice calls."

Include natural synonyms users say, such as "texting", "phone number", and "voice calls", to strengthen trigger-term coverage.

Mention inbound SMS polling capability so the description covers the full set of concrete actions the skill performs.

Dimension	Reasoning	Score
Specificity	"Provision Twilio numbers", "SMS/MMS", and "AI outbound calls" name several concrete capabilities in third person, matching the several-specific-actions anchor. It falls short of 5 because inbound SMS polling, direct Twilio calls, and provider selection (Bland/Vapi) are uncovered.	4 / 5
Completeness	The "what" is clear (provisioning numbers, SMS/MMS, AI outbound calls), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	Natural terms users would say — "Twilio", "SMS", "MMS", "calls" — are present, fitting the good-coverage anchor. Not 5 because common synonyms like "text/texting", "phone", and "voice" are missing.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear telephony/Twilio niche with distinct triggers ("Twilio", "SMS/MMS", "AI outbound calls"), making conflict with other skills unlikely. It clearly matches the clear-niche anchor.	5 / 5
	Total	16 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/productivity/telephony/SKILL.md
Commit: 68fa7e9

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.